Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Creator SKILL — Influencer Discovery deinai/deinai_backend AI influencer search on TikTok, Instagram, YouTube. Deinai MCP token required; credits per result. | |
| Creator SKILL v2 — Influencer Discovery deinai/skill-service SKILL-02 (not SKILL-01): AI influencer search on TikTok, Instagram & YouTube. sk_live_ token. | |
| Programscape deirfgeiz/programscape-mcp Startup credits, programs and perks from checked sources, with saved plans and reported balances. | |
| io.github.nicofains1/onlyswaps delegueinu/onlyswaps DEX meta-aggregator for AI agents. Best prices from 15+ aggregators across 13 chains. | |
| io.github.DELIGHT-LABS/walletconnect-mcp delight-labs/walletconnect-mcp Non-custodial EVM wallet bridge over WalletConnect: balances, signing, transactions. | |
| Deliverd Screen deliverd-dev/deliverd-sdk Find and redact personal data and secrets in text before it reaches a model. Local, no account. | |
| DeltaX Preflight deltax-public/deltax-preflight Check finite candidate proposals against separate policy and evidence, with canonical hash receipts. | |
| Planomy Planner demorphed6-lgtm/planomy-mcp Retirement planning on your own machine: projections, Monte Carlo, scenarios, budgets, plan edits. | |
| Machins Marketplace denizozzgur/agentrade Agent-to-agent marketplace with escrow-protected trades via MCP tools. | |
| com.feedback-magic/feedback-magic denneytech/feedbackmagic Create Feedback Magic widgets — feedback, surveys, changelog, roadmap — from your AI editor. | |
| io.github.DennisPrediger/slac-mcp dennisprediger/slac-mcp MCP server exposing SLAC (Simple Logic & Arithmetic Compiler) as tools for LLM agents | |
| Finekot API denyskot1986/finekot-api-mcp 89 pay-per-call tools for agents: screenshots, scraping, PDF, OCR, TTS, STT, invoices, KYC, utils | |
| Variafy denysvolynskyi/variafy-plugins Ad results, CRM revenue and account alerts for AI assistants. Meta changes are previewed first. | |
| macOS MCP Server deploymenttheory/macos-mcp-server Local macOS 27 desktop automation through MCP on Apple silicon. | |
| Kommo CRM depper-ia/kommo-kiro-power Manage Kommo CRM leads, contacts, pipelines, tasks, notes, tags and companies. | |
| io.github.derekchoyai/hone derekchoyai/hone Score your judgment over AI-assisted work. Hone scores you, not the model. | |
| Derive derive-to/derive Publish agent output to permanent versioned URLs, read review comments back, and revise. | |
| io.github.derNif/payanagent dernif/payanagent Buy any of 24,000+ live x402 services with USDC on Base — the open marketplace for the agent economy | |
| Game Industry Library derpbicycle/gil-mcp-bridge Search 300+ game industry reports with hybrid search, claims, charts, and citations. | |
| forthling deschaker/forthling Run Forth-2012 in a sandbox: definitions stay between calls, each result shows the stacks. | |
| FindA.Sale deseee/findasale Find yard sales, garage sales, auctions, flea markets and resale shops, and search items for sale. | |
| io.github.desper/quick-html-share-mcp desper/quick-html-sharing Share AI-generated HTML from your coding agent. Unguessable URL + viewer analytics. | |
| Agent Swarm desplega-ai/agent-swarm Full Agent Swarm API and MCP server with local SQLite storage for multi-agent orchestration. | |
| what2post destilabs/what2post-mcp Read-only access to your what2post LinkedIn data: posts, profile stats, follower growth and goals. | |
| Automo Build desygner/automo-build-mcp Operate Automo Build, the AI app builder, as yourself: projects, builds, QA, security, deployments. | |
| Detritus Site Services: Get a Quote detritus-llc/detritus-main Quote restrooms, trailers, handwash, tanks, dumpsters, fencing, storage, water, and power. | |
| ConnectIQ MCP Server deugene/connect-iq-mcp MCP server for Garmin ConnectIQ SDK documentation and resources | |
| Planner MCP — provable "done" for AI agents dev-lab-global/planner Goal and task planning MCP for Codex and AI agents, with evidence-backed completion. | |
| Attest dev-prathap/attest Decide by policy, gate behind a human, verify by read-back, record a hash-chained ledger. | |
| Paid MCP Metering dev55acc-ai/paid-mcp-metering Metered MCP tools: free discovery over MCP; per-call execution settled in USDC via x402 v2. | |
| ATSPrep devabubakar/atsprep-skills Free resume tools: ATS score, job match, bullet and LinkedIn checks, tailoring, interview prep. | |
| landmine devanshranjan10/landmines Known open GitHub issues in exact npm and PyPI versions, with workarounds, for coding agents. | |
| KSail devantler-tech/ksail SDK for creating, managing, and operating Kubernetes clusters and workloads with ease. | |
| JackTrade CRM devcham/jacktrade Search customers, manage quotes, work orders, action items, and calendar events for your business | |
| Website Screenshot & PDF devdeep-borisagar/website-screenshot-mcp Screenshot any website as PNG, JPEG, WebP, PDF or scrolling MP4/GIF video, with public file links. | |
| com.lightres/booking developermcconnected/lightrez Browse venues, check availability, view effects, get pricing, and book architectural lighting. | |
| Remode - Fashion Finder, New & Pre-loved deviljin17/remode Find fashion new or pre-loved from a photo, link or text; compare prices; hunt for a lower price. | |
| DevLens devlensio/devlensoss Query a precomputed code graph (nodes, edges, summaries) of TS/JS/React/Next.js/Node repos via MCP. | |
| be.florealholidays/workspace devliegerwout/florealsystem Floreal Holidays Belgium: live prices and availability; staff run M&E dossiers, day sheets, tasks. | |
| io.github.devlollc/torneo devlollc/gladiator Observatory operated and funded by devlo: real tools on frozen tasks; intervals, cost, limits. | |
| Stresix devmatei/stresix-mcp Load test your app on a real server from your agent. Get p95, errors and what ran out first. | |
| Engraphy devon-clarkk/engraphy Self-hosted MCP memory server: a typed knowledge graph on Postgres 16 and pgvector. | |
| io.github.devp1/personalinsights-feed devp1/personal_insights AI-classified tech/investor news feed with editorial verdicts, entities, and theses. | |
| SVGProof devreframe/vectorizer Turn a logo into a clean, print-ready SVG: from a web address, an upload or the upload card. | |
| io.github.devrobinransom/baos-mcp devrobinransom/baos-harness Read-only MCP access to a BAOS workspace: product graphs, requirements, evidence, research. | |
| ShadowCrawl devshero/shadowcrawl Stealth scraping & search. Bypasses Cloudflare, DataDome & LinkedIn via Cyborg HITL approach. | |
| LOCK IN — Social Media Addiction & Dopamine Reset devsrodrigo/lockin-mcp iOS dopamine detox app with social media blocking and screen time tools. | |
| GitHub CI/CD MCP Server devstephenke-sys/github-free-mcps GitHub CI/CD MCP server with 70 tools for repos, PRs, Actions, deployments, billing, and more. | |
| Adrails devthomy/adrails-mcp AI agent that runs Meta Ads and Google Ads for Shopify stores, with store revenue next to ad spend. | |
| Windframe devwares-team/windframe-mcp Provides style context & tokens to design or restyle web UIs in any framework |
22,401–22,450 of 50,909
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.